Convolutional Neural Network (CNNs)
The fifteenth entry in the AI red teaming series breaks down how CNNs process images and why their spatial assumptions create a structured adversarial playbook.
Neural networks
How neural networks learn through backpropagation, and why that same gradient mechanism powers adversarial examples, model inversion, and training data theft.
Perceptron
How the perceptron works, where it breaks, and why its limitations define the attack surfaces of every neural network. Part of the AI red teaming series.
Deep learning
Deep Learning: How neural networks train, why backpropagation is also an attack vector, and what gradients mean for adversarial ML.
Q-learning
How Q-learning agents build decision policies from reward signals, and why every component of the Bellman update is a vector for adversarial manipulation.
Reinforcement learning
How reinforcement learning agents train through interaction, and why controlling the environment or reward signal is all an adversary needs.
Anomaly detection
How One-Class SVM, Isolation Forest, and LOF work, why their training data is the real attack surface, and what red teamers gain from understanding an anomaly.
K-means clustering
How K-means clustering works, why its centroid mechanics are trivially exploitable, and what red teamers need to know about attacking unsupervised ML models.
Unsupervised learning
How red teamers exploit unsupervised learning models: poisoning, mimicry, and baseline drift attacks against clustering and anomaly detection.